Trustworthy AI in the Digital Economy: Practices and Explorations by Ant Group

In a keynote at the Machine Heart AI Technology Conference, Ant Group's Zhou Jun presented the concept of trustworthy AI, detailing its integration with privacy, security, graph learning, explainable and adversarial machine learning, and large‑scale privacy‑preserving techniques to enhance financial risk control in the digital economy.

Explainable Machine LearningPrivacy-Preserving MLadversarial learning

0 likes · 20 min read

Trustworthy AI in the Digital Economy: Practices and Explorations by Ant Group

Xianyu Technology

Jun 4, 2020 · Artificial Intelligence

NBDT: Neural-Backed Decision Trees for Interpretable Image Classification

NBDT (Neural‑Backed Decision Trees) merges a pretrained CNN with a WordNet‑derived hierarchical tree, using the network’s final‑layer weights as class embeddings and a combined classification loss, to deliver state‑of‑the‑art image classification that remains interpretable through explicit hierarchical reasoning.

CNNDecision TreesExplainable Machine Learning

0 likes · 11 min read

NBDT: Neural-Backed Decision Trees for Interpretable Image Classification